UMCUtrecht-ECGxAI/ecgxai
Neatly packaged AI methods for explainable ECG analysis
This project helps medical researchers and cardiologists better understand why AI models make specific diagnoses from electrocardiograms (ECGs). It takes standard 12-lead ECG recordings as input and produces either a disease diagnosis or prediction, along with interpretable 'factors' that explain the AI's reasoning. The primary users are researchers developing AI for cardiology and clinicians seeking clearer explanations for AI-driven ECG insights.
No commits in the last 6 months.
Use this if you need to train AI models for ECG analysis and require clear, interpretable explanations for their diagnostic or predictive outputs, rather than just a 'black box' answer.
Not ideal if you are looking for a pre-built, ready-to-use clinical diagnostic tool, as this is a research package for developing and evaluating explainable AI methods.
Stars
94
Forks
23
Language
Python
License
AGPL-3.0
Category
Last pushed
Oct 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/UMCUtrecht-ECGxAI/ecgxai"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
DeepPSP/torch_ecg
Deep learning ECG models implemented using PyTorch
im-ethz/flirt
Are you ready to FLIRT with your wearable data?
Edoar-do/HuBERT-ECG
A self-supervised foundation ECG model for broad and scalable cardiac applications
AmbiqAI/heartkit
Perform AI-based heart monitoring tasks
bowang-lab/ecg-fm
An electrocardiogram analysis foundation model.